mimicus_interact

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond the annotations: 'non-destructive click' and 'same-origin reviewed navigation' constrain behavior despite openWorldHint=true, which is genuinely useful context. The renew semantics (bounded idle lease, compact state with no image, cannot extend absolute lifetime) disclose a non-obvious side effect. Missing only rate/size/positioning constraints on the interaction itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, action inventory front-loaded, zero filler. The renew caveat is the right content but appended in a way that reads as a secondary clause rather than a structured note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The presence of an output schema relieves it of explaining return values, and the safety/lease behavior is covered. However, for a deeply nested 15-field interaction object at 0% schema coverage, the description leaves too much for the agent to guess on coordinates, selectors, and three unlisted actions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the burden, and it does not. It maps roughly to the action enum but silently omits wait, touch, and drag, and says nothing about selector, x/y coordinates, endX/endY drag targets, steps, or waitMs. The agent must reverse-engineer 15 undocumented nested fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb set (hover, click, focus, scroll, pointer, navigate, key, resize, renew) against a specific resource (a selected page/session). The scope — safe, non-destructive interaction on an already-selected page — is clear. It does not explicitly distinguish itself from close siblings like mimicus_explore_page or mimicus_capture_view, leaving the agent to infer boundaries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'selected page' implies a prerequisite (a session established elsewhere), and the renew clause implies when to use it versus a full interaction. But there is no explicit when-to-use/when-not or named alternative among the 16 siblings, several of which (explore_page, capture_view, capture_motion) plausibly overlap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.